update_corpus

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It adds useful behavioral context: full mode is slow, and it discloses return value ('返回本次新增与当前库存统计'). However, it does not address side effects (articles written to DB), rate limits, or reversibility, which matter for a tool that mutates a corpus. It covers some traits but not enough for zero-annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences with zero filler; the primary purpose is front-loaded before the mode caveat. Slightly terse but efficient—every clause earns its place given there are only two parameters to cover.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no annotations and no output schema, the description covers purpose, mode distinction, time-cost, and a return summary. The notable gap is max_articles, which has no explanation anywhere, and the return-value description is vague ('本次新增与当前库存统计' leaves the stats format unspecified). Adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains the full parameter clearly (re-walks the entire list, slow, initial-setup-only), which is valuable. But max_articles (an integer with default 300, presumably a safety cap on batch size) is never mentioned, leaving a second parameter effectively undocumented at zero schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise verb+resource+scope: '增量抓取:发现并抓取数据库尚未收录的最新文章' (incremental fetch: discover and fetch the latest articles not yet cataloged). It clearly distinguishes the fetching/mutation role from the read-oriented siblings (search, get_article, list_articles, corpus_stats), so an agent can tell them apart immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear mode-selection guidance: it marks full=True as only-for-initial-setup/proofreading and explicitly warns it is time-consuming ('仅初建/校对用,耗时长'), which tells the agent when to avoid it. It does not explicitly name sibling alternatives or state when-not-to-use, but the context for the two modes is substantive and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.